Axle detection and Counting

  • For the project UH4SP Unified Hub for smart plants at CCG, I have developed an axle detection and counting system. This system helps to analyse and classify the type of vehicle entering the industry.The class for different vehicles are given described below. In addition to axle detection, I have also deployed the Automatic Licence Plate recogntion using OpenALPR to classify the vehicles.
  • The Green box in the video is the ROI - Region of interest. To make the application computationally efficient,I choose apply axle detection only in ROI.
  • This application detects axle based on Houghcircle Transform.
  • This system also performs well in real time detection and counting.

Ps : Due to work restrictions only preliminary results of two different videos are shown below.

In [1]:
import cv2 
import numpy as np 

Video 1

In [4]:
import io
import base64
from IPython.display import HTML
video = io.open('outpy.mp4', 'r+b').read()
encoded = base64.b64encode(video)
HTML(data='''<video width="640" height="420"  alt="test" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii')))
Out[4]:

Video 2

In [7]:
from IPython.display import HTML
video = io.open('car2.mp4', 'r+b').read()
encoded = base64.b64encode(video)
HTML(data='''<video width="640" height="420"  alt="test" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii')))
Out[7]:

Fish Detection Tracking and Recognition

  • This is my intership work with University Paris 7.
  • Biologist would like to study the behviour of different fishes and species. Keeping this in context, we developed this application for studying each fishes individually.
  • For an European project assisi-project.eu. Designed and developed a fish detection and tracking algorithm from high resolution videos.
  • From the fish group videos, I extracted the spatial coordinates of each fish to study the behavior mechanisms in groups and studied inter individuality distribution of fishes in groups.
  • This project is funded by http://assisi-project.eu/
  • This work is more helpfull in studying the movement pattern of fishes.
In [10]:
from IPython.display import HTML
video = io.open('fish1.mp4', 'r+b').read()
encoded = base64.b64encode(video)
HTML(data='''<video width="640" height="420"  alt="test" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii')))
Out[10]:

Face Recognition and clustering

  • My PhD thesis is about unsupervised character recognition in Tv Series. The idea is to find the characters speaking in the video.
  • The first key idea is to detect the faces and then apply visual voice activity detection.
  • The face detection and recogntion is done using OpenFace library. The below video just shows the detection of faces and clustering part will be added soon.
  • It uses Dlib, Torch, Opencv and hierarchical clustering.
  • Even in the bad quality videos it detects faces
In [25]:
from IPython.display import HTML
video = io.open('finaloviya.mp4', 'r+b').read()
encoded = base64.b64encode(video)
HTML(data='''<video width="640" height="420"  alt="test" controls><source src="data:video/mp4;base64,{0}" type="video/mp4" /></video>'''.format(encoded.decode('ascii')))
Out[25]:

Please click here to see good qulality video Video. Clic Open it in VLC